检索结果-内蒙古大学图书馆

60th Annual Conference of the Society-of-Instrument-and-Control-Engineers-of-Japan (SICE)

作者： Wei, Zeyi Zhang, Yahui Yanshan Univ Coll Mech Engn Qinhuangdao Peoples R China

ISBN: (纸本)9784907764739

This paper proposes an energy management strategy (EMS) for connected power-split hybrid electric vehicles (HEVs). In detail, long short-term memory networks (LSTM) is used to predict the future velocity trajectory for a few seconds of the preceding vehicle by utilizing the information provided by vehicle to vehicle (V2V) and vehicle to infrastructure (V2I). Then consumption of fuel and electricity are chosen as the cost function of the optimization. And model predictive control (MPC) approach is adopted to optimize the cost function. In order to solve the problem of dimension explosion, the cost-to-go function is optimized through approximate dynamic programming (ADP). Finally, the effectiveness of EMS is verified on the platform of MATLAB/Simulink.

关键词： Energy management strategy hybrid electric vehicles long short-term memory networks fuel economy approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Managing Fragmented Fire-Threatened Landscapes with Spatial Externalities

引用

FOREST SCIENCE 2020年第4期66卷 443-456页

作者： Lauer, Christopher J. Montgomery, Claire A. Dietterich, Thomas G. NOAA 1315 East West Highway Silver Spring MD 20910 USA Oregon State Univ Forest Engn Resources & Management 280 Peary Hall Corvallis OR 97331 USA Oregon State Univ Elect Engn & Comp Sci 1148 Kelley Engn Ctr Corvallis OR 97331 USA

Accounting for externalities generated by fire spread is necessary for managing fire risk on landscapes with multiple owners. In this paper, we determine the optimal management of a synthetic landscape parameterized to represent the ecological conditions of Douglas-fir (Pseudotsuga menziesii) plantations in southwest Oregon. The problem is formulated as a dynamic game, where each agent maximizes their own objective without considering the welfare of the other agents. We demonstrate a method for incorporating spatial information and externalities into a dynamic optimization process. A machine-learning technique, approximate dynamic programming, is applied to determine the optimal timing and location of fuel treatments and timber harvests for each agent. The value functions we estimate explicitly account for the spatial interactions that generate fire risk. They provide a way to model the expected benefits, costs, and externalities associated with management actions that have uncertain consequences in multiple locations. The method we demonstrate is applied to analyze the effect of landscape fragmentation on landowner welfare and ecological outcomes. Study Implications: This research builds on several important ideas for forest management. Fire risk for any particular stand on a landscape is a function of vegetation conditions across the entire landscape. Landowners who wish to achieve a management objective that is affected by fire risk need to account for the risk generated by broader landscape conditions. This work expands on a tractable model to account for the spatial interactions generated by fire spread that affect the optimal timing and spatial location of timber harvest and fuel treatments. In this paper, we demonstrate that optimal behavior changes when there are multiple landowners. On a sufficiently fragmented landscape, one landowner's actions can create additional risk for their neighbors. This work suggests that policy interventions to incentivize risk

关键词： wildland fire stochastic dynamic games spatial ecological disturbance risk approximate dynamic programming multiagent reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-driven optimal control with a relaxed linear program

引用

AUTOMATICA 2022年 136卷

作者： Martinelli, Andrea Gargiani, Matilde Lygeros, John Swiss Fed Inst Technol Automatic Control Lab Physikstrasse 3 CH-8092 Zurich Switzerland

The linear programming (LP) approach has a long history in the theory of approximate dynamic programming. When it comes to computation, however, the LP approach often suffers from poor scalability. In this work, we introduce a relaxed version of the Bellman operator for q-functions and prove that it is still a monotone contraction mapping with a unique fixed point. In the spirit of the LP approach, we exploit the new operator to build a relaxed linear program (RLP). Compared to the standard LP formulation, our RLP has only one family of constraints and half the decision variables, making it more scalable and computationally efficient. For deterministic systems, the RLP trivially returns the correct q-function. For stochastic linear systems in continuous spaces, the solution to the RLP preserves the minimizer of the optimal q-function, hence retrieves the optimal policy. Theoretical results are backed up in simulation where we solve sampled versions of the LPs with data collected by interacting with the environment. For general nonlinear systems, we observe that the RLP again tends to preserve the minimizers of the solution to the LP, though the relative performance is influenced by the specific geometry of the problem. (c) 2021 The Authors. Published by Elsevier Ltd.

关键词： approximate dynamic programming Optimal control Data-driven control Linear programming Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Stochastic one-way carsharing systems with dynamic relocation incentives through preference learning

引用

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW 2022年 166卷

作者： Liu, Yang Xie, Jiaohong Chen, Nan Natl Univ Singapore Dept Ind Syst Engn & Management 1 Engn Dr 2 Singapore 117576 Singapore Natl Univ Singapore Dept Civil & Environm Engn 1 Engn Dr 2 Singapore 117576 Singapore

The development of carsharing services is expected to achieve greater resource efficiency and provide a sustainable solution for future mobility systems. However, operators inevitably face the imbalance between demand and supply in one-way carsharing systems (CSSs). Also, it is challenging for them to make quick and efficient operational decisions when both travel time and trip requests are uncertain. This study leverages historical and online data and proposes a learning-based methodology to quickly make real-time decisions for CSSs, including vehicle assignment, relocation, and user incentive decisions. Compared to the literature in approximate dynamic programming (ADP), which mostly focuses on uncertainty in trip requests, we propose an offline-online ADP approach to consider the temporal and spatial uncertainty in both trip requests and travel time. To tackle our high-dimensional problem, we integrate an online look-ahead policy into the offline value function approximation (VFA) policy to produce a computational tractable high-quality dynamic fleet management policy. Furthermore, a user -based relocation strategy is investigated to rebalance the fleet distribution to meet the demand better. Specifically, we aim to solve the optimal incentives the operator could offer to users to relocate cars, while user preferences towards relocation incentives are generally unknown in practice. We further enhance our anticipatory policy by developing an online module via Bayesian learning that learns the preference model on the fly using users' revealed preference data collected online. The numerical experiments in Singapore demonstrate our offline-online ADP approach improves the solution quality and significantly compared to offline VFA policy. The results also confirm the importance of incorporating uncertainty in travel time. The benefits of the user-based relocation scheme using the Bayesian learning method using online data to enhance anticipatory decisions and learn un

关键词： One-way carsharing approximate dynamic programming Online decision-making User-based vehicle relocation User preference learning Urban mobility operations

来源：评论

学校读者我要写书评

暂无评论

An expected-cost realization-probability optimization approach for the dynamic energy management of microgrid

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2022年 136卷

作者： Zhu, Jianquan Zhuo, Yelin Chen, Jiajun Guo, Ye Mo, Xiemin Liu, Mingbo South China Univ Technol Sch Elect Power Engn Guangzhou 510640 Peoples R China

dynamic energy management (DEM) is being recognized as an important tool for the economical and efficient operation of microgrid. This paper proposes an expected-cost realization-probability (ECRP) optimization approach for the DEM of microgrid. In the model, the expected cost is taken as an economic goal to find the schedule with the maximum ECRP (i.e., the maximum probability of obtaining an actual operation cost which is lower than this economic goal). It is a stochastic mixed-integer nonlinear programming (MINLP) problem composed of the AC power flow, battery operation characters and logical variables. To solve this NP-hard problem, an ECRP-based approximate dynamic programming is proposed. The original MINLP problem is decomposed into small nonlinear programming subproblems to facilitate the solution. And the ECRP-based value function is formed to describe the relationship among the decisions of subproblems, which helps to obtain the near-optimal decision in a decomposed manner. Simulation examples presented on a real microgrid indicate that the ECRP of the proposed method is higher than those of the other two comparison algorithms.

关键词： approximate dynamic programming dynamic energy management Expected cost Microgrid Realization probability

来源：评论

学校读者我要写书评

暂无评论

dynamic stochastic electric vehicle routing with safe reinforcement learning

引用

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW 2022年 157卷

作者： Basso, Rafael Kulcsar, Balazs Sanchez-Diaz, Ivan Qu, Xiaobo Volvo Grp Trucks Technol Gothenburg Sweden Chalmers Univ Technol Elect Engn Gothenburg Sweden Chalmers Univ Technol Technol Management & Econ Gothenburg Sweden Chalmers Univ Technol Architecture & Civil Engn Gothenburg Sweden

dynamic routing of electric commercial vehicles can be a challenging problem since besidesthe uncertainty of energy consumption there are also random customer requests. This paperintroduces the dynamic Stochastic Electric Vehicle Routing Problem (DS-EVRP). A Safe Rein-forcement Learning method is proposed for solving the problem. The objective is to minimizeexpected energy consumption in a safe way, which means also minimizing the risk of batterydepletion while en route by planning charging whenever necessary. The key idea is to learnoffline about the stochastic customer requests and energy consumption using Monte Carlosimulations, to be able to plan the route predictively and safely online. The method is evaluatedusing simulations based on energy consumption data from a realistic traffic model for the cityof Luxembourg and a high-fidelity vehicle model. The results indicate that it is possible tosave energy at the same time maintaining reliability by planning the routes and charging in ananticipative way. The proposed method has the potential to improve transport operations withelectric commercial vehicles capitalizing on their environmental benefits.

关键词： Reinforcement learning approximate dynamic programming Electric vehicles Energy consumption Vehicle routing Green logistics

来源：评论

学校读者我要写书评

暂无评论

approximate Information State for approximate Planning and Reinforcement Learning in Partially Observed Systems

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2022年 23卷 1-83页

作者： Subramanian, Jayakumar Sinha, Amit Seraj, Raihan Mahajan, Aditya Adobe Syst India Private Ltd Digital Experience Cloud Media & Data Sci Res Lab Plot A5Noida Greater Noida ExpresswayBlock A Noida 201304 Uttar Pradesh India McGill Univ Dept Elect & Comp Engn 3480 Univ St Montreal PQ H3A 0E9 Canada

We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundamental notion of information state. We provide two definitions of information state i) a function of history which is sufficient to compute the expected reward and predict its next value;ii) a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show that if a function of the history (called approximate information state (AIS)) approximately satisfies the properties of the information state, then there is a corresponding approximate dynamic program. We show that the policy computed using this is approximately optimal with bounded loss of optimality. We show that several approximations in state, observation and action spaces in literature can be viewed as instances of AIS. In some of these cases, we obtain tighter bounds. A salient feature of AIS is that it can be learnt from data. We present AIS based multi-time scale policy gradient algorithms and detailed numerical experiments with low, moderate and high dimensional environments.

关键词： Partially observed reinforcement learning partially observable Markov decision processes approximate dynamic programming information state approximate information state

来源：评论

学校读者我要写书评

暂无评论

dynamic Fleet Management for Autonomous Vehicles: Learning- and optimization-based strategies

Dynamic Fleet Management for Autonomous Vehicles: Learning- ...

引用

作者： Alves Beirigo, B. Delft University of Technology

学位级别：博士

Autonomous vehicles (AVs) have been heralded as the key to unlock a shared mobility future where transportation is more efficient, convenient, and cheaper. However, the AV utopia can only come to fruition if the majority of users trust that autonomous mobility-on-demand (AMoD) systems are on a par with owning a vehicle in terms of service quality. Once the perception of quality is highly subjective, we propose a more personalized approach to on-demand mobility, in which users are segmented into service quality classes. These classes comprise minimum requirements regarding responsiveness and privacy, allowing us to model a series of user profiles formalized using strict service quality contracts. By honoring these contracts, providers can build users' trust and gain their loyalty, which on a grander scheme can contribute to a faster transition to a shared mobility *** thesis presents a series of strategies to guaranteeing service quality throughout operational scenarios arising in the timeline of AV technology deployment. First, a precondition to providing service quality in autonomous transportation is safety. During a transition phase to full automation, AV operation will likely be restricted to areas where safe operations are guaranteed, leading to the formation of hybrid street networks comprised of autonomous and non-autonomous vehicle zones. In this setting, meeting user service quality expectations is primarily a matter of coverage, once mobility services will have to access both AV-ready and not AV-ready areas. Accordingly, this thesis proposes solutions to overcome the challenges entailed by such a transition scenario, where infrastructures, regulatory measures, and AV technology are gradually ***, assuming that widespread automated driving is the new status quo, we set out to model rich autonomous transportation scenarios comprised of heterogeneous users and vehicles. Central to our analysis is finding an adequate tradeoff between fleet si

关键词： dynamic fleet management autonomous vehicles service quality on-demand hiring autonomous vehicle zone people and freight integration mobility poverty mobility-on-demand approximate dynamic programming matheuristic mixed integer programming

来源：评论

学校读者我要写书评

暂无评论

Safe model-based reinforcement learning for nonlinear optimal control with state and input constraints

引用

AICHE JOURNAL 2022年第5期68卷

作者： Kim, Yeonsoo Kim, Jong Woo Kwangwoon Univ Dept Chem Engn 20 Kwangwoon Ro Seoul 01897 South Korea Tech Univ Berlin Chair Bioproc Engn Berlin Germany

Safety is a critical factor in reinforcement learning (RL) in chemical processes. In our previous work, we had proposed a new stability-guaranteed RL for unconstrained nonlinear control-affine systems. In the approximate policy iteration algorithm, a Lyapunov neural network (LNN) was updated while being restricted to the control Lyapunov function, and a policy was updated using a variation of Sontag's formula. In this study, we additionally consider state and input constraints by introducing a barrier function, and we extend the applicable type to general nonlinear systems. We augment the constraints into the objective function and use the LNN added with a Lyapunov barrier function to approximate the augmented value function. Sontag's formula input with this approximate function brings the states into its lower level set, thereby guaranteeing the constraints satisfaction and stability. We prove the practical asymptotic stability and forward invariance. The effectiveness is validated using four tank system simulations.

关键词： approximate dynamic programming barrier function control Lyapunov function reinforcement learning Sontag's formula

来源：评论

学校读者我要写书评

暂无评论

Solving the dynamic ambulance relocation and dispatching problem using approximate dynamic programming

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2012年第3期219卷 611-621页

作者： Schmid, Verena Univ Vienna Dept Business Adm A-1210 Vienna Austria

Emergency service providers are supposed to locate ambulances such that in case of emergency patients can be reached in a time-efficient manner. Two fundamental decisions and choices need to be made real-time. First of all immediately after a request emerges an appropriate vehicle needs to be dispatched and send to the requests' site. After having served a request the vehicle needs to be relocated to its next waiting location. We are going to propose a model and solve the underlying optimization problem using approximate dynamic programming (ADP), an emerging and powerful tool for solving stochastic and dynamic problems typically arising in the field of operations research. Empirical tests based on real data from the city of Vienna indicate that by deviating from the classical dispatching rules the average response time can be decreased from 4.60 to 4.01 minutes, which corresponds to an improvement of 12.89%. Furthermore we are going to show that it is essential to consider time-dependent information such as travel times and changes with respect to the request volume explicitly. Ignoring the current time and its consequences thereafter during the stage of modeling and optimization leads to suboptimal decisions. (C) 2011 Elsevier B.V. All rights reserved.

关键词： OR in health services Emergency vehicles Ambulance location approximate dynamic programming Stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：